Files
kami 2ca5ffa4f9 capture: answer the stop before summarising, and always leave a note
capture_stop held the IPC request open for the whole map reduce, up to
twenty minutes. A voice turn that says "хватит" waited for forty model
calls before Maven said anything. Stop now returns the transcript and the
summary runs on a goroutine in the daemon's WaitGroup, on the daemon
context so a client that hung up does not cancel the only readable record
of the meeting.

With no summary and save_transcript false, writeNotes wrote nothing at
all: an hour of meeting left a blob that prunes in seven days and no
trace in the note store. The transcript is written instead when the
summary is missing. That flag decides whether the verbatim record is kept
in addition to a summary, not whether the meeting is remembered.

The wire carries the session token now, and the contract comments say
what the code does: the summary is usually absent from the stop
response, and re running a stored blob is a manual job because no method
takes a blob id. The save_transcript comment says the cost is recall
corpus rather than disk.

Found in review of #73.
2026-08-01 14:36:17 +04:00

261 lines
8.7 KiB
Go

package config
import (
"encoding/json"
"testing"
"time"
)
// Absent blocks must read as off on a nil receiver: the daemon calls these
// helpers before it knows whether the operator configured anything.
func TestSensesOffByDefault(t *testing.T) {
var cfg Config
if cfg.Media.StoreDir() != "" {
t.Error("media store dir is set with no media block")
}
if cfg.Vision.LooksAtImages() {
t.Error("vision is on with no vision block")
}
if cfg.Capture.Records() {
t.Error("the recorder is on with no capture block")
}
if cfg.Capture.MaxDuration() != 0 {
t.Error("a nil capture block invented a duration")
}
if cfg.Speaker.Recognizes() {
t.Error("speaker recognition is on with no speaker block")
}
}
// The recorder is the capability that most needs its default to be off, so it
// gets its own test rather than a line in the one above.
func TestCaptureIsOffUntilExplicitlyEnabled(t *testing.T) {
cases := []struct {
name string
c *CaptureConfig
want bool
}{
{"absent", nil, false},
{"present but not enabled", &CaptureConfig{MaxMinutes: 60}, false},
{"enabled", &CaptureConfig{Enabled: true}, true},
}
for _, c := range cases {
if got := c.c.Records(); got != c.want {
t.Errorf("%s: Records() = %v, want %v", c.name, got, c.want)
}
}
}
func TestCaptureBlockParsesFromJSON(t *testing.T) {
raw := `{"capture":{"enabled":true,"max_minutes":45,"stt_window":"2m",
"chunk_runes":2000,"max_chunks":10,"save_transcript":true}}`
var cfg Config
if err := json.Unmarshal([]byte(raw), &cfg); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if !cfg.Capture.Records() {
t.Fatal("capture did not parse as enabled")
}
if cfg.Capture.MaxDuration() != 45*time.Minute {
t.Errorf("max duration = %v", cfg.Capture.MaxDuration())
}
if time.Duration(cfg.Capture.STTWindow) != 2*time.Minute {
t.Errorf("stt window = %v", time.Duration(cfg.Capture.STTWindow))
}
if cfg.Capture.ChunkRunes != 2000 || cfg.Capture.MaxChunks != 10 {
t.Errorf("summariser limits = %+v", cfg.Capture)
}
if !cfg.Capture.SaveTranscript {
t.Error("save_transcript did not parse")
}
}
// Keeping the verbatim record of what other people said is the heavier act, so
// it is separately opt-in from recording at all.
func TestTranscriptIsNotSavedByDefault(t *testing.T) {
var cfg Config
if err := json.Unmarshal([]byte(`{"capture":{"enabled":true}}`), &cfg); err != nil {
t.Fatal(err)
}
if cfg.Capture.SaveTranscript {
t.Error("transcripts are saved without anyone asking")
}
if cfg.Capture.MaxDuration() != 0 {
t.Error("max_minutes defaulted in config instead of in the package")
}
}
// enabled with nothing to talk to is a misconfiguration, not a capability.
func TestVisionNeedsBothEnabledAndEndpoint(t *testing.T) {
cases := []struct {
name string
v *VisionConfig
want bool
}{
{"absent", nil, false},
{"endpoint but not enabled", &VisionConfig{Endpoint: "http://127.0.0.1:8081"}, false},
{"enabled but no endpoint", &VisionConfig{Enabled: true}, false},
{"enabled, blank endpoint", &VisionConfig{Enabled: true, Endpoint: " "}, false},
{"both", &VisionConfig{Enabled: true, Endpoint: "http://127.0.0.1:8081"}, true},
}
for _, c := range cases {
if got := c.v.LooksAtImages(); got != c.want {
t.Errorf("%s: LooksAtImages() = %v, want %v", c.name, got, c.want)
}
}
}
func TestSensesBlocksParseFromJSON(t *testing.T) {
raw := `{
"db_path": "/tmp/x.db",
"socket_path": "/tmp/x.sock",
"media": {"dir": "media", "retention": "48h", "max_bytes": 1048576},
"vision": {
"enabled": true,
"endpoint": "http://127.0.0.1:8081",
"model": "qwen2.5-vl",
"max_dim": 640,
"max_tokens": 200,
"timeout": "45s",
"prompt": "Что тут?"
}
}`
var cfg Config
if err := json.Unmarshal([]byte(raw), &cfg); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if cfg.Media.StoreDir() != "media" {
t.Errorf("media dir = %q", cfg.Media.StoreDir())
}
if time.Duration(cfg.Media.Retention) != 48*time.Hour {
t.Errorf("retention = %v", time.Duration(cfg.Media.Retention))
}
if cfg.Media.MaxBytes != 1<<20 {
t.Errorf("max_bytes = %d", cfg.Media.MaxBytes)
}
if !cfg.Vision.LooksAtImages() {
t.Fatal("vision did not parse as enabled")
}
if cfg.Vision.MaxDim != 640 || cfg.Vision.MaxTokens != 200 {
t.Errorf("vision limits = %+v", cfg.Vision)
}
if time.Duration(cfg.Vision.Timeout) != 45*time.Second {
t.Errorf("vision timeout = %v", time.Duration(cfg.Vision.Timeout))
}
if cfg.Vision.Prompt != "Что тут?" {
t.Errorf("prompt = %q", cfg.Vision.Prompt)
}
}
// A media dir set with no vision block is a valid state, and the useful one on a
// box with no vision model: images can be kept, they just cannot be described.
func TestMediaWithoutVisionIsValid(t *testing.T) {
var cfg Config
if err := json.Unmarshal([]byte(`{"media":{"dir":"/srv/media"}}`), &cfg); err != nil {
t.Fatal(err)
}
if cfg.Media.StoreDir() != "/srv/media" {
t.Errorf("dir = %q", cfg.Media.StoreDir())
}
if cfg.Vision.LooksAtImages() {
t.Error("vision came on by itself")
}
}
// A voiceprint is a biometric of a named person. Nothing about it turns on by
// itself: no speaker block means no recognition, and no enrolment either.
func TestSpeakerIsOffUntilExplicitlyEnabled(t *testing.T) {
var cfg Config
if err := json.Unmarshal([]byte(`{}`), &cfg); err != nil {
t.Fatal(err)
}
if cfg.Speaker.Recognizes() {
t.Error("speaker recognition came on with no config at all")
}
var empty Config
if err := json.Unmarshal([]byte(`{"speaker":{}}`), &empty); err != nil {
t.Fatal(err)
}
if empty.Speaker.Recognizes() {
t.Error("an empty speaker block enabled recognition")
}
}
// Enabled alone is not enough: recognition needs a model, and on this box there
// is none. Recognizes() must stay false so the daemon reports the honest state
// instead of claiming a capability it cannot perform.
func TestSpeakerNeedsBothEnabledAndAModel(t *testing.T) {
var cfg Config
if err := json.Unmarshal([]byte(`{"speaker":{"enabled":true}}`), &cfg); err != nil {
t.Fatal(err)
}
if cfg.Speaker.Recognizes() {
t.Error("enabled with no model_path claimed to recognise")
}
var only Config
if err := json.Unmarshal([]byte(`{"speaker":{"model_path":"/opt/x.onnx"}}`), &only); err != nil {
t.Fatal(err)
}
if only.Speaker.Recognizes() {
t.Error("a model_path alone enabled recognition")
}
}
func TestSpeakerBlockParsesFromJSON(t *testing.T) {
const raw = `{"speaker":{"enabled":true,"model_path":"/opt/maven/models/spk/ecapa.onnx",` +
`"lib_path":"/opt/maven/lib","threshold":0.62,"min_seconds":1.5}}`
var cfg Config
if err := json.Unmarshal([]byte(raw), &cfg); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if !cfg.Speaker.Recognizes() {
t.Fatal("speaker did not parse as enabled")
}
if cfg.Speaker.ModelPath != "/opt/maven/models/spk/ecapa.onnx" {
t.Errorf("model_path = %q", cfg.Speaker.ModelPath)
}
if cfg.Speaker.LibPath != "/opt/maven/lib" {
t.Errorf("lib_path = %q", cfg.Speaker.LibPath)
}
if cfg.Speaker.Threshold != 0.62 || cfg.Speaker.MinSeconds != 1.5 {
t.Errorf("thresholds = %+v", cfg.Speaker)
}
}
// A typo in the vision endpoint, or a media block with no dir, used to be
// logged once at wiring time and the capability just stayed off. A capability
// that silently does not exist is the hardest misconfiguration to notice, so
// both fail at startup now.
func TestSensesBlocksAreValidatedAtStartup(t *testing.T) {
bad := map[string]string{
"media with no dir": `{"media":{"retention":"48h"}}`,
"negative budget": `{"media":{"dir":"/srv/media","max_total_bytes":-1}}`,
"blob over the budget": `{"media":{"dir":"/srv/media","max_bytes":100,"max_total_bytes":10}}`,
"vision with no media dir": `{"vision":{"enabled":true,"endpoint":"http://127.0.0.1:8081"}}`,
"vision endpoint typo": `{"media":{"dir":"/srv/media"},"vision":{"enabled":true,"endpoint":"127.0.0.1:8081"}}`,
"vision on the wan": `{"media":{"dir":"/srv/media"},"vision":{"enabled":true,"endpoint":"http://8.8.8.8:8081"}}`,
"vision, empty endpoint": `{"media":{"dir":"/srv/media"},"vision":{"enabled":true}}`,
"capture with no store": `{"capture":{"enabled":true}}`,
}
for name, body := range bad {
t.Run(name, func(t *testing.T) {
if _, err := Load(writeConfig(t, body)); err == nil {
t.Fatal("want a startup error")
}
})
}
good := map[string]string{
"media alone": `{"media":{"dir":"/srv/media"}}`,
"media + vision": `{"media":{"dir":"/srv/media"},"vision":{"enabled":true,"endpoint":"http://127.0.0.1:8081"}}`,
"media + capture": `{"media":{"dir":"/srv/media"},"capture":{"enabled":true}}`,
"vision off": `{"vision":{"endpoint":"http://8.8.8.8:8081"}}`,
}
for name, body := range good {
t.Run(name, func(t *testing.T) {
if _, err := Load(writeConfig(t, body)); err != nil {
t.Fatalf("valid config refused: %v", err)
}
})
}
}